BUG DataFrameGroupBy.agg with list not respecting as_index=False (pandas-dev#53237)

* fix dataframegroupby.agg not respecting as_index=false

* cleaned up code, removed breakpoints

* cleaning up codes

* final cleanup of code, ready for review, sry abt that

* resolve typing (not sure)

* used better approach

* new test added; enh short circuiting

* clean up code

Author: Charlie-XIAO

doc/source/whatsnew/v2.1.0.rst

@@ -455,6 +455,7 @@ Groupby/resample/rolling
   grouped :class:`Series` or :class:`DataFrame` was a :class:`DatetimeIndex`, :class:`TimedeltaIndex`
   or :class:`PeriodIndex`, and the ``groupby`` method was given a function as its first argument,
   the function operated on the whole index rather than each element of the index. (:issue:`51979`)
+- Bug in :meth:`DataFrameGroupBy.agg` with lists not respecting ``as_index=False`` (:issue:`52849`)
 - Bug in :meth:`DataFrameGroupBy.apply` causing an error to be raised when the input :class:`DataFrame` was subset as a :class:`DataFrame` after groupby (``[['a']]`` and not ``['a']``) and the given callable returned :class:`Series` that were not all indexed the same. (:issue:`52444`)
 - Bug in :meth:`DataFrameGroupBy.apply` raising a ``TypeError`` when selecting multiple columns and providing a function that returns ``np.ndarray`` results (:issue:`18930`)
 - Bug in :meth:`GroupBy.groups` with a datetime key in conjunction with another key produced incorrect number of group keys (:issue:`51158`)

pandas/core/groupby/generic.py

@@ -44,6 +44,7 @@
     is_bool,
     is_dict_like,
     is_integer_dtype,
+    is_list_like,
     is_numeric_dtype,
     is_scalar,
 )
@@ -1397,7 +1398,11 @@ def aggregate(self, func=None, *args, engine=None, engine_kwargs=None, **kwargs)
         op = GroupByApply(self, func, args=args, kwargs=kwargs)
         result = op.agg()
         if not is_dict_like(func) and result is not None:
-            return result
+            # GH #52849
+            if not self.as_index and is_list_like(func):
+                return result.reset_index()
+            else:
+                return result
         elif relabeling:
             # this should be the only (non-raising) case with relabeling
             # used reordered index of columns

pandas/tests/groupby/aggregate/test_aggregate.py

@@ -1586,3 +1586,16 @@ def test_agg_multiple_with_as_index_false_subset_to_a_single_column():
     result = gb.agg(["sum", "mean"])
     expected = DataFrame({"a": [1, 2], "sum": [7, 5], "mean": [3.5, 5.0]})
     tm.assert_frame_equal(result, expected)
+
+
+def test_agg_with_as_index_false_with_list():
+    # GH#52849
+    df = DataFrame({"a1": [0, 0, 1], "a2": [2, 3, 3], "b": [4, 5, 6]})
+    gb = df.groupby(by=["a1", "a2"], as_index=False)
+    result = gb.agg(["sum"])
+
+    expected = DataFrame(
+        data=[[0, 2, 4], [0, 3, 5], [1, 3, 6]],
+        columns=MultiIndex.from_tuples([("a1", ""), ("a2", ""), ("b", "sum")]),
+    )
+    tm.assert_frame_equal(result, expected)

pandas/tests/groupby/test_categorical.py

@@ -2067,11 +2067,8 @@ def test_agg_list(request, as_index, observed, reduction_func, test_series, keys
     if as_index and (test_series or reduction_func == "size"):
         expected = expected.to_frame(reduction_func)
     if not test_series:
-        if not as_index:
-            # TODO: GH#52849 - as_index=False is not respected
-            expected = expected.set_index(keys)
-        expected.columns = MultiIndex(
-            levels=[["b"], [reduction_func]], codes=[[0], [0]]
+        expected.columns = MultiIndex.from_tuples(
+            [(ind, "") for ind in expected.columns[:-1]] + [("b", reduction_func)]
         )
     elif not as_index:
         expected.columns = keys + [reduction_func]